EP 3816999 B1 20221109 - NEURAL NETWORK BASED DETERMINATION OF THE DIRECTION OF ARRIVAL OF VOICE
Title (en)
NEURAL NETWORK BASED DETERMINATION OF THE DIRECTION OF ARRIVAL OF VOICE
Title (de)
NEURAL NETZWERK BASIERTE EINFALLSRICHTUNGSBESTIMMUNG VON SPRACHE
Title (fr)
DÉTERMINATION DE LA DIRECTION D'ARRIVÉE DE LA PAROLE BASÉE SUR UN RÉSEAU NEURONAL
Publication
Application
Priority
CN 202010697058 A 20200720
Abstract (en)
[origin: EP3816999A2] The present disclosure provides a method and apparatus for detecting a voice, relates to the fields of voice processing and deep learning technology. A specific embodiment includes: acquiring a target voice; and inputting the target voice into a pre-trained deep neural network to obtain whether the target voice has a sub-voice in each of a plurality of preset direction intervals, the deep neural network being used to predict whether the voice has a sub-voice in each of the plurality of direction intervals. The present disclosure may predict each direction interval separately, so as to accurately determine whether the target voice has a sub-voice in each direction interval, to realize accurate prediction.
IPC 8 full level
G10L 25/78 (2013.01); G10L 25/30 (2013.01)
CPC (source: CN EP KR US)
G10L 15/02 (2013.01 - KR US); G10L 15/063 (2013.01 - KR); G10L 25/30 (2013.01 - CN EP KR US); G10L 25/78 (2013.01 - CN EP KR US)
Designated contracting state (EPC)
AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR
DOCDB simple family (publication)
EP 3816999 A2 20210505; EP 3816999 A3 20211020; EP 3816999 B1 20221109; CN 111863036 A 20201030; CN 111863036 B 20220301; JP 2022017170 A 20220125; JP 7406521 B2 20231227; KR 102599978 B1 20231108; KR 20220011064 A 20220127; US 2021210113 A1 20210708
DOCDB simple family (application)
EP 21163855 A 20210322; CN 202010697058 A 20200720; JP 2021047560 A 20210322; KR 20210031674 A 20210310; US 202117208387 A 20210322